[FFmpeg-devel] [PATCH 10/21] aarch64: hevc: Produce epel_hv functions for both plain neon and i8mm
Martin Storsjö
martin at martin.st
Mon Mar 25 17:02:32 EET 2024
AWS Graviton 3:
put_hevc_epel_hv4_8_c: 163.7
put_hevc_epel_hv4_8_neon: 52.5
put_hevc_epel_hv4_8_i8mm: 49.5
put_hevc_epel_hv6_8_c: 292.2
put_hevc_epel_hv6_8_neon: 97.7
put_hevc_epel_hv6_8_i8mm: 101.2
put_hevc_epel_hv8_8_c: 471.0
put_hevc_epel_hv8_8_neon: 106.7
put_hevc_epel_hv8_8_i8mm: 102.5
put_hevc_epel_hv12_8_c: 1030.2
put_hevc_epel_hv12_8_neon: 240.5
put_hevc_epel_hv12_8_i8mm: 215.0
put_hevc_epel_hv16_8_c: 1711.5
put_hevc_epel_hv16_8_neon: 340.2
put_hevc_epel_hv16_8_i8mm: 319.2
put_hevc_epel_hv24_8_c: 3670.0
put_hevc_epel_hv24_8_neon: 702.0
put_hevc_epel_hv24_8_i8mm: 666.5
put_hevc_epel_hv32_8_c: 6785.5
put_hevc_epel_hv32_8_neon: 1247.0
put_hevc_epel_hv32_8_i8mm: 1169.0
put_hevc_epel_hv48_8_c: 14689.7
put_hevc_epel_hv48_8_neon: 2665.2
put_hevc_epel_hv48_8_i8mm: 2740.0
put_hevc_epel_hv64_8_c: 25899.2
put_hevc_epel_hv64_8_neon: 4801.2
put_hevc_epel_hv64_8_i8mm: 4487.7
---
libavcodec/aarch64/hevcdsp_epel_neon.S | 58 +++++++++++++----------
libavcodec/aarch64/hevcdsp_init_aarch64.c | 6 +++
2 files changed, 38 insertions(+), 26 deletions(-)
diff --git a/libavcodec/aarch64/hevcdsp_epel_neon.S b/libavcodec/aarch64/hevcdsp_epel_neon.S
index 2088630da1..024464723b 100644
--- a/libavcodec/aarch64/hevcdsp_epel_neon.S
+++ b/libavcodec/aarch64/hevcdsp_epel_neon.S
@@ -2298,10 +2298,8 @@ function hevc_put_hevc_epel_hv24_8_end_neon
2: ret
endfunc
-#if HAVE_I8MM
-ENABLE_I8MM
-
-function ff_hevc_put_hevc_epel_hv4_8_neon_i8mm, export=1
+.macro epel_hv suffix
+function ff_hevc_put_hevc_epel_hv4_8_\suffix, export=1
add w10, w3, #3
lsl x10, x10, #7
sub sp, sp, x10 // tmp_array
@@ -2310,13 +2308,13 @@ function ff_hevc_put_hevc_epel_hv4_8_neon_i8mm, export=1
add x0, sp, #32
sub x1, x1, x2
add w3, w3, #3
- bl X(ff_hevc_put_hevc_epel_h4_8_neon_i8mm)
+ bl X(ff_hevc_put_hevc_epel_h4_8_\suffix)
ldp x0, x3, [sp, #16]
ldp x5, x30, [sp], #32
b hevc_put_hevc_epel_hv4_8_end_neon
endfunc
-function ff_hevc_put_hevc_epel_hv6_8_neon_i8mm, export=1
+function ff_hevc_put_hevc_epel_hv6_8_\suffix, export=1
add w10, w3, #3
lsl x10, x10, #7
sub sp, sp, x10 // tmp_array
@@ -2325,13 +2323,13 @@ function ff_hevc_put_hevc_epel_hv6_8_neon_i8mm, export=1
add x0, sp, #32
sub x1, x1, x2
add w3, w3, #3
- bl X(ff_hevc_put_hevc_epel_h6_8_neon_i8mm)
+ bl X(ff_hevc_put_hevc_epel_h6_8_\suffix)
ldp x0, x3, [sp, #16]
ldp x5, x30, [sp], #32
b hevc_put_hevc_epel_hv6_8_end_neon
endfunc
-function ff_hevc_put_hevc_epel_hv8_8_neon_i8mm, export=1
+function ff_hevc_put_hevc_epel_hv8_8_\suffix, export=1
add w10, w3, #3
lsl x10, x10, #7
sub sp, sp, x10 // tmp_array
@@ -2340,13 +2338,13 @@ function ff_hevc_put_hevc_epel_hv8_8_neon_i8mm, export=1
add x0, sp, #32
sub x1, x1, x2
add w3, w3, #3
- bl X(ff_hevc_put_hevc_epel_h8_8_neon_i8mm)
+ bl X(ff_hevc_put_hevc_epel_h8_8_\suffix)
ldp x0, x3, [sp, #16]
ldp x5, x30, [sp], #32
b hevc_put_hevc_epel_hv8_8_end_neon
endfunc
-function ff_hevc_put_hevc_epel_hv12_8_neon_i8mm, export=1
+function ff_hevc_put_hevc_epel_hv12_8_\suffix, export=1
add w10, w3, #3
lsl x10, x10, #7
sub sp, sp, x10 // tmp_array
@@ -2355,13 +2353,13 @@ function ff_hevc_put_hevc_epel_hv12_8_neon_i8mm, export=1
add x0, sp, #32
sub x1, x1, x2
add w3, w3, #3
- bl X(ff_hevc_put_hevc_epel_h12_8_neon_i8mm)
+ bl X(ff_hevc_put_hevc_epel_h12_8_\suffix)
ldp x0, x3, [sp, #16]
ldp x5, x30, [sp], #32
b hevc_put_hevc_epel_hv12_8_end_neon
endfunc
-function ff_hevc_put_hevc_epel_hv16_8_neon_i8mm, export=1
+function ff_hevc_put_hevc_epel_hv16_8_\suffix, export=1
add w10, w3, #3
lsl x10, x10, #7
sub sp, sp, x10 // tmp_array
@@ -2370,13 +2368,13 @@ function ff_hevc_put_hevc_epel_hv16_8_neon_i8mm, export=1
add x0, sp, #32
sub x1, x1, x2
add w3, w3, #3
- bl X(ff_hevc_put_hevc_epel_h16_8_neon_i8mm)
+ bl X(ff_hevc_put_hevc_epel_h16_8_\suffix)
ldp x0, x3, [sp, #16]
ldp x5, x30, [sp], #32
b hevc_put_hevc_epel_hv16_8_end_neon
endfunc
-function ff_hevc_put_hevc_epel_hv24_8_neon_i8mm, export=1
+function ff_hevc_put_hevc_epel_hv24_8_\suffix, export=1
add w10, w3, #3
lsl x10, x10, #7
sub sp, sp, x10 // tmp_array
@@ -2385,79 +2383,87 @@ function ff_hevc_put_hevc_epel_hv24_8_neon_i8mm, export=1
add x0, sp, #32
sub x1, x1, x2
add w3, w3, #3
- bl X(ff_hevc_put_hevc_epel_h24_8_neon_i8mm)
+ bl X(ff_hevc_put_hevc_epel_h24_8_\suffix)
ldp x0, x3, [sp, #16]
ldp x5, x30, [sp], #32
b hevc_put_hevc_epel_hv24_8_end_neon
endfunc
-function ff_hevc_put_hevc_epel_hv32_8_neon_i8mm, export=1
+function ff_hevc_put_hevc_epel_hv32_8_\suffix, export=1
stp x4, x5, [sp, #-64]!
stp x2, x3, [sp, #16]
stp x0, x1, [sp, #32]
str x30, [sp, #48]
mov x6, #16
- bl X(ff_hevc_put_hevc_epel_hv16_8_neon_i8mm)
+ bl X(ff_hevc_put_hevc_epel_hv16_8_\suffix)
ldp x0, x1, [sp, #32]
ldp x2, x3, [sp, #16]
ldp x4, x5, [sp], #48
add x0, x0, #32
add x1, x1, #16
mov x6, #16
- bl X(ff_hevc_put_hevc_epel_hv16_8_neon_i8mm)
+ bl X(ff_hevc_put_hevc_epel_hv16_8_\suffix)
ldr x30, [sp], #16
ret
endfunc
-function ff_hevc_put_hevc_epel_hv48_8_neon_i8mm, export=1
+function ff_hevc_put_hevc_epel_hv48_8_\suffix, export=1
stp x4, x5, [sp, #-64]!
stp x2, x3, [sp, #16]
stp x0, x1, [sp, #32]
str x30, [sp, #48]
mov x6, #24
- bl X(ff_hevc_put_hevc_epel_hv24_8_neon_i8mm)
+ bl X(ff_hevc_put_hevc_epel_hv24_8_\suffix)
ldp x0, x1, [sp, #32]
ldp x2, x3, [sp, #16]
ldp x4, x5, [sp], #48
add x0, x0, #48
add x1, x1, #24
mov x6, #24
- bl X(ff_hevc_put_hevc_epel_hv24_8_neon_i8mm)
+ bl X(ff_hevc_put_hevc_epel_hv24_8_\suffix)
ldr x30, [sp], #16
ret
endfunc
-function ff_hevc_put_hevc_epel_hv64_8_neon_i8mm, export=1
+function ff_hevc_put_hevc_epel_hv64_8_\suffix, export=1
stp x4, x5, [sp, #-64]!
stp x2, x3, [sp, #16]
stp x0, x1, [sp, #32]
str x30, [sp, #48]
mov x6, #16
- bl X(ff_hevc_put_hevc_epel_hv16_8_neon_i8mm)
+ bl X(ff_hevc_put_hevc_epel_hv16_8_\suffix)
ldp x4, x5, [sp]
ldp x2, x3, [sp, #16]
ldp x0, x1, [sp, #32]
add x0, x0, #32
add x1, x1, #16
mov x6, #16
- bl X(ff_hevc_put_hevc_epel_hv16_8_neon_i8mm)
+ bl X(ff_hevc_put_hevc_epel_hv16_8_\suffix)
ldp x4, x5, [sp]
ldp x2, x3, [sp, #16]
ldp x0, x1, [sp, #32]
add x0, x0, #64
add x1, x1, #32
mov x6, #16
- bl X(ff_hevc_put_hevc_epel_hv16_8_neon_i8mm)
+ bl X(ff_hevc_put_hevc_epel_hv16_8_\suffix)
ldp x0, x1, [sp, #32]
ldp x2, x3, [sp, #16]
ldp x4, x5, [sp], #48
add x0, x0, #96
add x1, x1, #48
mov x6, #16
- bl X(ff_hevc_put_hevc_epel_hv16_8_neon_i8mm)
+ bl X(ff_hevc_put_hevc_epel_hv16_8_\suffix)
ldr x30, [sp], #16
ret
endfunc
+.endm
+
+epel_hv neon
+
+#if HAVE_I8MM
+ENABLE_I8MM
+
+epel_hv neon_i8mm
DISABLE_I8MM
#endif
diff --git a/libavcodec/aarch64/hevcdsp_init_aarch64.c b/libavcodec/aarch64/hevcdsp_init_aarch64.c
index be24737c9c..87e321da71 100644
--- a/libavcodec/aarch64/hevcdsp_init_aarch64.c
+++ b/libavcodec/aarch64/hevcdsp_init_aarch64.c
@@ -227,6 +227,10 @@ NEON8_FNPROTO(epel_h, (int16_t *dst,
const uint8_t *_src, ptrdiff_t _srcstride,
int height, intptr_t mx, intptr_t my, int width),);
+NEON8_FNPROTO(epel_hv, (int16_t *dst,
+ const uint8_t *src, ptrdiff_t srcstride,
+ int height, intptr_t mx, intptr_t my, int width), );
+
NEON8_FNPROTO(epel_h, (int16_t *dst,
const uint8_t *_src, ptrdiff_t _srcstride,
int height, intptr_t mx, intptr_t my, int width), _i8mm);
@@ -407,6 +411,8 @@ av_cold void ff_hevc_dsp_init_aarch64(HEVCDSPContext *c, const int bit_depth)
NEON8_FNASSIGN_SHARED_32(c->put_hevc_epel, 0, 1, epel_h,);
NEON8_FNASSIGN_SHARED_32(c->put_hevc_epel_uni_w, 0, 1, epel_uni_w_h,);
+ NEON8_FNASSIGN(c->put_hevc_epel, 1, 1, epel_hv,);
+
if (have_i8mm(cpu_flags)) {
NEON8_FNASSIGN(c->put_hevc_epel, 0, 1, epel_h, _i8mm);
NEON8_FNASSIGN(c->put_hevc_epel, 1, 1, epel_hv, _i8mm);
--
2.39.3 (Apple Git-146)
More information about the ffmpeg-devel
mailing list